xuehao.ma (@dog-qiuqiu)
github

dog-qiuqiu

Twitter logo Share LinkedIn logo Share Facebook logo Share
  • Stars
    star
    7,307
  • Global Rank 3,339 (Top 0.2 %)
  • Followers 560
  • Following 1
  • Registered over 4 years ago
  • Most used languages
    C++
         50.0 %
    Python
         30.0 %
    C
         20.0 %
  • Location 🇨🇳 China
  • Country Total Rank 743
  • Country Ranking
    C
         49
    Python
         409
    C++
         1,253

Top repositories

1

Yolo-Fastest

âš¡ Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+
C
1,985
star
2

MobileNet-Yolo

MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥
C
1,706
star
3

Yolo-FastestV2

âš¡ Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+
Python
797
star
4

FastestDet

⚡ A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler
Python
760
star
5

Ultralight-SimplePose

Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,
Python
290
star
6

simple-rknn2

The rknn2 API uses the secondary encapsulation of the process, which is easy for everyone to call. It is applicable to rk356x rk3588
C++
42
star
7

Android_NCNN_yolov4-tiny

yolov4-tiny ncnn android sample
C++
37
star
8

Android_MobileNetV2-YOLOV3-Nano-NCNN

MobileNetV2-YOLOV3-Nano NCNN sample
C++
21
star
9

libopencv

Opencv ARM Linux precompiled library
C++
11
star
10

Simple-TensorRT

Secondary encapsulation of NVIDIA TensorRT interface to simplify the calling process
C++
9
star
11

dog-qiuqiu

2
star